© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29046
    Prev
    Next
    INDEX
    Explanations

    biofilms, animation, or computer interfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŀ¶
    -0.07
    纲
    -0.06
    çī¹æ®ĬçļĦ
    -0.06
    æħİ
    -0.06
    对幼åĦ¿
    -0.06
    æľį
    -0.06
    arangan
    -0.06
    igm
    -0.06
    èĩªçIJĨ
    -0.06
    å¤ĦçIJĨçļĦ
    -0.06
    POSITIVE LOGITS
    ÙĪÙĦÙĬ
    0.08
    iveau
    0.08
    ENDOR
    0.08
    ẹn
    0.08
    _ARM
    0.07
     Sem
    0.07
    ×Ļת×Ļ
    0.07
    erman
    0.07
    çIJª
    0.07
    åľ¨åįĬ
    0.07
    Activations Density 0.422%

    No Known Activations